Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Skin Cancer

Skin Cancer

Skin cancer is a type of cancer that occurs when there is an abnormal growth of skin cells, usually triggered by damage to the DNA within the skin cells. It is primarily caused by exposure to ultraviolet (UV) radiation from the sun or artificial sources like tanning beds. Skin cancer is the most common type of cancer worldwide, and its incidence continues to rise.
Basal Cell Carcinoma (BCC): BCC is the most common type of skin cancer, accounting for about 80% of cases. It typically develops in...

Pigmentation

Pigmentation

The color of the skin is influenced by a number of pigments, including melanin, carotene, and hemoglobin. Recall that melanin is produced by cells called melanocytes, which are found scattered throughout the stratum basale of the epidermis. The melanin is transferred to the keratinocytes via melanosomes.
Melanin occurs in two primary forms: eumelanin that provides black and brown pigment and pheomelanin that provides red color. Dark-skinned individuals produce more melanin than those with pale...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Comparison of Ketorolac at 3 Doses in Children With Acute Pain: Protocol for A Randomized Controlled Trial.

JMIR research protocols·2025

Same author

Topical non-steroidal anti-inflammatory drug use for pediatric acute musculoskeletal pain: a scoping review.

CJEM·2025

Same author

Just the facts: Shiga toxin-producing Escherichia coli infection in children.

CJEM·2025

Same author

Methodological standards in the design and reporting of pilot and feasibility studies in emergency medicine literature: a systematic review.

BMJ open·2024

Same author

Interpretable Skin Cancer Classification based on Incremental Domain Knowledge Learning.

Journal of healthcare informatics research·2023

Same author

Novel care pathway to optimise antimicrobial prescribing for uncomplicated community-acquired pneumonia: study protocol for a prospective before-after cohort study in the emergency department of a tertiary care Canadian children's hospital.

BMJ open·2022

Search research articles

Related Experiment Video

Updated: Jun 9, 2025

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

Improving Skin Color Diversity in Cancer Detection: Deep Learning Approach.

Eman Rezk¹, Mohamed Eltorki², Wael El-Dakhakhni¹

¹School of Computational Science and Engineering, McMaster University, Hamilton, ON, Canada.

JMIR Dermatology

|October 30, 2024

Summary

Deep learning generates realistic darker skin lesion images, improving AI diagnosis for people of color. This enhances dermatology data diversity and diagnostic accuracy for skin conditions.

Keywords:

algorithm artificial intelligence cancer computer-generated data augmentation deep learning dermatology diagnosis diagnostic digital health generalizability generated image image generation imaging lesion machine learning neural network skin skin cancer diagnosis skin tone diversity

More Related Videos

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jun 9, 2025

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Dermatology
Artificial Intelligence
Medical Imaging

Background:

Dermatology resources lack dark skin images, hindering diagnosis for people of color.
AI applications are biased due to training primarily on light skin images.

Purpose of the Study:

Develop a deep learning approach to generate realistic darker skin lesion images.
Enhance dermatology data diversity for improved diagnostic accuracy.

Main Methods:

Utilized style transfer (ST) and deep blending (DB) deep learning methods.
Generated darker skin images from lighter skin images.
Evaluated image realism and disease presentation quantitatively and qualitatively.
Trained a convolutional neural network (CNN) with generated images to assess impact on classification.

Main Results:

Style transfer (ST) outperformed deep blending (DB) in realism and disease similarity.
ST-generated images were perceived as real by 62.2% of masked participants.
Dermatologists achieved 75% accuracy diagnosing lesions in ST-generated images.
CNN model using generated images showed improved classification accuracy (0.76) and AUC (0.72).

Conclusions:

Deep learning effectively generates realistic skin lesion images, increasing dermatology atlas diversity.
Diversified image datasets improve the generalizability of AI diagnostic applications for skin cancer.